Upload config.json with huggingface_hub
Browse files- config.json +44 -0
config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 5120,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 13824,
|
| 12 |
+
"max_position_embeddings": 1010000,
|
| 13 |
+
"max_window_layers": 48,
|
| 14 |
+
"model_type": "qwen2",
|
| 15 |
+
"num_attention_heads": 40,
|
| 16 |
+
"num_hidden_layers": 48,
|
| 17 |
+
"num_key_value_heads": 8,
|
| 18 |
+
"rms_norm_eps": 1e-05,
|
| 19 |
+
"rope_scaling": null,
|
| 20 |
+
"rope_theta": 10000000.0,
|
| 21 |
+
"sliding_window": 1010000,
|
| 22 |
+
"tie_word_embeddings": false,
|
| 23 |
+
"torch_dtype": "bfloat16",
|
| 24 |
+
"transformers_version": "4.45.2",
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"use_sliding_window": false,
|
| 27 |
+
"vocab_size": 152064,
|
| 28 |
+
"dual_chunk_attention_config": {
|
| 29 |
+
"chunk_size": 262144,
|
| 30 |
+
"local_size": 8192,
|
| 31 |
+
"original_max_position_embeddings": 262144
|
| 32 |
+
},
|
| 33 |
+
"quantization_config": {
|
| 34 |
+
"quant_method": "exl2",
|
| 35 |
+
"version": "0.2.7",
|
| 36 |
+
"bits": 8.0,
|
| 37 |
+
"head_bits": 8,
|
| 38 |
+
"calibration": {
|
| 39 |
+
"rows": 115,
|
| 40 |
+
"length": 2048,
|
| 41 |
+
"dataset": "(default)"
|
| 42 |
+
}
|
| 43 |
+
}
|
| 44 |
+
}
|